Data processing device, data processing method, and data processing program

Abstract

To provide a data processing device, method, and program for appropriately responding to user inputs.SOLUTION: In a data processing system 10, a data processing device is configured to: input, upon receiving a creation sentence as input data, a prompt including a problem solvable by its content and an indication for creating a summary of the creation sentence, as a first prompt, to a data generation model; acquire the result of first specific processing; input, when the input data is a search query, a prompt including the query and an indication for querying the intent of search of a browsing user assumed therefrom, as a second prompt, to the data generation model; acquire the result of second specific processing; input a prompt including an indication for querying a list of summaries associated with the problem corresponding to the intent of search corresponding to the second prompt, as a third prompt, to the data generation model; acquire the result of third specific processing; and output the result of third specific processing and the creation sentence when having acquired interest information.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The technology disclosed herein relates to a data processing device, a data processing method, and a data processing program. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the prior art leaves room for improvement in responding appropriately to user input. [Means for solving the problem]

[0005] A data processing device of a first aspect includes an acquisition unit that acquires input data indicating a user input, a processing unit that performs a specific process using a generative model that generates information according to the input data, and an output unit that outputs a result of the specific process to an electronic device, wherein the acquisition unit acquires a created sentence that is a sentence created by a first user as the input data, and the processing unit inputs the created sentence acquired by the acquisition unit and a prompt including an instruction to generate a problem that can be solved by the content of the created sentence and a summary of the created sentence as a first prompt to the generative model, generates a problem and a summary corresponding to the first prompt, associates the generated problem and summary corresponding to the first prompt with the created sentence, and stores them in a memory unit, and the processing unit acquires the created sentence acquired by the acquisition unit as the input data. A prompt including a search query and an instruction to inquire about the search intention of a second user assumed from the search query is input into the generative model as a second prompt, thereby generating a search intention corresponding to the second prompt, and a prompt including an instruction to inquire about a list of abstracts associated with an issue corresponding to the generated search intention corresponding to the second prompt is input into the generative model as a third prompt, thereby generating a list of abstracts corresponding to the third prompt, and the output unit outputs the list of abstracts corresponding to the third prompt generated by the processing unit to the electronic device, and when the acquisition unit acquires the input data indicating the second user's interest in a specific abstract in the list of abstracts, outputs the created text associated with the specific abstract to the electronic device.

[0006] A data processing device of a second aspect is a data processing device of the first aspect, wherein the processing unit associates the task and summary corresponding to the generated first prompt, the created text, and the first user in the memory unit, and includes an awarding unit that awards a reward to the first user who created the created text associated with the summary output to the electronic device, and to the first user who created the created text output to the electronic device.

[0007] A data processing device of a third aspect is the data processing device of the first or second aspect, wherein the processing unit fine-tunes the generative model using a pair of a task and a summary corresponding to the first prompt as training data.

[0008] A data processing device of a fourth aspect is a data processing device of the second or third aspect, and when the similarity of the multiple created sentences stored in the memory unit is equal to or greater than a predetermined value and the multiple created sentences are created by different first users, the data processing device is provided with a notification unit that notifies an initial user, who is the first user who created the created sentence that was first acquired by the acquisition unit among the multiple created sentences, of the existence of a similar created sentence, and when the acquisition unit acquires a deletion instruction from the initial user as the input data, the processing unit deletes from the memory unit the created sentences created by the other first users that are similar to the created sentences created by the initial user.

[0009] A data processing device of a fifth aspect is a data processing device of any of the first to fourth aspects, wherein the processing unit inputs a prompt including the search query, the browsing history of the created text by the second user, and an instruction to inquire about the search intention into the generative model as the second prompt, and generates a search intention corresponding to the second prompt.

[0010] A data processing device of a sixth aspect is a data processing device of any one of the first to fifth aspects, wherein the acquisition unit acquires user information indicating attributes of the second user as the input data, and the output unit outputs to the electronic device a list of summaries excluding the inappropriate summaries when the list of summaries corresponding to the third prompt generated by the processing unit includes inappropriate summaries that are not suitable for the attributes of the second user indicated by the user information.

[0011] A data processing method of a seventh aspect includes acquiring input data indicating a user input, performing a specification process using a generative model that generates information according to the input data, outputting a result of the specification process to an electronic device, acquiring a created sentence that is a sentence created by a first user as the input data, inputting the acquired created sentence and a prompt including an instruction to generate a problem that can be solved by the content of the created sentence and a summary of the created sentence as a first prompt to the generative model, generating a problem and a summary corresponding to the first prompt, associating the generated problem and summary corresponding to the first prompt with the created sentence and storing them in a storage unit, and acquiring a search query acquired as the input data and a problem that can be solved by the content of the created sentence and a summary of the created sentence assumed from the search query. the computer executes the process of: inputting a prompt including an instruction to inquire about the search intention of a second user to the generative model as a second prompt, generating a search intention corresponding to the second prompt; inputting a prompt including an instruction to inquire about a list of abstracts associated with a task corresponding to the generated search intention corresponding to the second prompt as a third prompt, generating a list of abstracts corresponding to the third prompt; outputting the generated list of abstracts corresponding to the third prompt to the electronic device; and, if the input data indicating the second user's interest in a specific abstract in the list of abstracts is obtained, outputting the created text associated with the specific abstract to the electronic device.

[0012] A data processing program according to an eighth aspect of the present invention includes: acquiring input data indicating a user input; performing a specification process using a generative model that generates information according to the input data; outputting a result of the specification process to an electronic device; acquiring a created sentence that is a sentence created by a first user as the input data; inputting the acquired created sentence and a prompt including an instruction to generate a problem that can be solved by the content of the created sentence and a summary of the created sentence as a first prompt to the generative model; generating a problem and a summary corresponding to the first prompt; storing the generated problem and summary corresponding to the first prompt in a storage unit in association with the created sentence; and inputting a prompt including an instruction to inquire about the search intention of a second user to be searched for and an instruction to inquire about the search intention of a second user to be searched for, into the generative model as a second prompt, thereby generating a search intention corresponding to the second prompt, inputting a prompt including an instruction to inquire about a list of abstracts associated with a task corresponding to the generated search intention corresponding to the second prompt as a third prompt, thereby generating a list of abstracts corresponding to the third prompt, outputting the generated list of abstracts corresponding to the third prompt to the electronic device, and, if the input data indicating an interest of the second user in a specific abstract in the list of abstracts is obtained, outputting the created text associated with the specific abstract to the electronic device. [Brief description of the drawings]

[0013] [Figure 1] FIG. 1 is a conceptual diagram illustrating an example of a configuration of a data processing system. [Diagram 2] FIG. 2 is a conceptual diagram showing an example of main functions of a data processing device and a smart device. [Diagram 3] 1 is a first block diagram showing an example of a functional configuration of a specific processing unit. FIG. [Figure 4] 13 is an example of an operational flow regarding an operation of a specific processing unit performing a first specific processing. [Diagram 5] 13 is an example of an operational flow regarding an operation of the identification processing unit performing a second identification process and a third identification process. [Figure 6] 13 is a first display example displayed on a display of a smart device. [Figure 7] 13 is a second display example shown on the display of a smart device. [Figure 8] 13 is a second block diagram showing an example of a functional configuration of a specific processing unit. FIG. [Figure 9] 1 shows a first emotion map onto which multiple emotions are mapped. [Figure 10] 13 shows a second emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] Hereinafter, an example of an embodiment of a data processing device, a data processing method, and a data processing program according to the technique of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained. In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0016] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0017] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0018] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0020] (First embodiment) First, a first embodiment of a data processing system 10 according to the embodiment will be described.

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the embodiment. As shown in Fig. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. An example of the smart device 14 is a smartphone. In this embodiment, the data processing device 12 is an example of a "data processing device" according to the technology of the present disclosure, and the smart device 14 is an example of an "electronic device" according to the technology of the present disclosure.

[0022] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0023] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0024] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits input data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the input data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that a human user can perceive (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. Position data 45 is stored in the camera 42.

[0026] The communication I / F 44 is connected to a network 54. The communication I / F 44 and the communication I / F 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0027] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "data processing program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores a data generation model 58 and an emotion identification model 60. The data generation model 58 and the emotion identification model 60 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 62. The reception output program 62 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 62 from the storage 50, and executes the read reception output program 62 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 62 executed on the RAM 48.

[0031] Here, an application (hereinafter, "specific application") is installed in the smart device 14 that allows a posting user to post a created text, which is a text created by the posting user, and allows the viewing user to view the created text. Among the users of the smart device 14, a posting user who posts a created text can post the created text by executing the specific application and performing a predetermined operation. Among the users of the smart device 14, a viewing user who views the created text can view the created text by executing the specific application and performing a predetermined operation. The created text includes explanatory texts such as explanatory texts, editorial texts, and critical essays, and literary texts such as narrative texts, essays, and poems. The posting user is an example of a "first user" according to the technology of the present disclosure, and the viewing user is an example of a "second user" according to the technology of the present disclosure.

[0032] The data processing device 12 also stores the created text posted by the posting user in the database 24. Then, the data processing device 12 acquires the created text based on the search query input to the specific application from the database 24 and outputs the created text to the smart device 14 of the browsing user who input the search query. The database 24 is an example of a "storage unit" according to the technology of the present disclosure.

[0033] Next, a description will be given of the processing of the specific processing unit 290 when the data processing device 12 performs a specific processing for generating information corresponding to input data indicating a user input. Fig. 3 is a first block diagram showing an example of the functional configuration of the specific processing unit 290.

[0034] As shown in FIG. 3, the specific processing unit 290 includes an acquisition unit 290A, a processing unit 290B, an output unit 290C, and an assignment unit 290D.

[0035] The acquiring unit 290A acquires input data indicating a user input accepted by the smart device 14. Specifically, the acquiring unit 290A acquires input data based on a user's text input, voice input, and the like accepted by the smart device 14. In addition, the acquiring unit 290A acquires a composition sentence created by the posting user as input data.

[0036] The processing unit 290B performs a specific process using the data generation model 58. The data generation model 58 is a so-called generation AI (Artificial Intelligence). An example of the data generation model 58 is a generation AI such as ChatGPT. Note that ChatGPT is, for example, an Internet search<URL: https: / / openai.com / blog / chatgpt> and internet searches<URL: https: / / aismiley.co.jp / ai_news / chatgpt-tsukattemita / > Since this is publicly known as disclosed in, for example, US Pat. No. 6,399,343, detailed description thereof will be omitted.

[0037] The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The data generation model 58 is an example of a "generation model" according to the technology of the present disclosure.

[0038] The above-mentioned identification process includes a first identification process for generating a problem that can be solved by the content of the created text and a summary of the created text as information corresponding to the input data, a second identification process for generating a search intent of the browsing user assumed from the search query as the information, and a third identification process for generating a list of summaries associated with the problem corresponding to the search intent. The above-mentioned problem can solve certain problems faced by humans, such as relieving fatigue, relieving pain, losing weight, and building muscle. The above-mentioned summary includes at least one of the title and summary of the created text. In the following, as an example, the summary of the created text will be described as the "title of the created text."

[0039] Then, the processing unit 290B inputs a prompt including the created sentence acquired by the acquisition unit 290A and an instruction to generate a problem that can be solved by the content of the created sentence and a title for the created sentence into the data generation model 58 as a first prompt, and generates a problem and title corresponding to the first prompt.

[0040] Furthermore, the processing unit 290B stores in the database 24 an assignment and title corresponding to the generated first prompt, the created sentence on which the assignment and title are based, and the posting user who created the created sentence in association with each other. As a result, each created sentence is linked to its assignment and title, and the posting user who created it. The processing unit 290B then fine-tunes the data generation model 58 using the pair of assignment and title corresponding to the generated first prompt as learning data. For example, the processing unit 290B may store an assignment and title corresponding to the generated first prompt in the form of learning data, such as a combination of an assignment and title corresponding to an Internet search.<URL: https: / / www.brainpad.co.jp / doors / knowledge / 01_chatgpt_fine_tuning_internal_documents / > and internet searches<URL: https: / / di-acc2.com / programming / python / 25924 / > The data generation model 58 is fine-tuned by appropriately using known techniques such as those disclosed in the above publications.

[0041] Furthermore, the processing unit 290B inputs a prompt including the search query acquired by the acquisition unit 290A as input data and an instruction to inquire about the search intention of the browsing user assumed from the search query as a second prompt to the data generation model 58, and generates a search intention corresponding to the second prompt. The search query is a phrase input by the browsing user to a specific application, and in this embodiment, the search query is a "sentence." The search intention is the purpose of the browsing user assumed from the search query, such as wanting to relieve fatigue, wanting to relieve pain, wanting to lose weight, and wanting to build muscle.

[0042] The processor 290B also inputs a prompt including an instruction to inquire about a list of titles associated with the problem corresponding to the search intent corresponding to the generated second prompt as a third prompt to the data generation model 58, and generates a list of titles corresponding to the third prompt. The problem corresponding to the search intent is, for example, a problem that can solve the purpose of the browsing user, such as "relieve fatigue" when the search intent is "I want to relieve fatigue."

[0043] The output unit 290C outputs the result of the identification process to the smart device 14. Specifically, the output unit 290C outputs a list of titles corresponding to the third prompt generated by the processing unit 290B to the smart device 14. As a result, the list of titles is displayed on the display 40A of the smart device 14. In addition, when the acquisition unit 290A acquires input data (hereinafter, "interest information") indicating the interest of the browsing user in a specific title in the list of titles, the output unit 290C outputs a created sentence associated with the specific title to the smart device 14. As a result, the created sentence is displayed on the display 40A of the smart device 14. Note that the interest information is input data in which the specific title and a predetermined phrase indicating interest, such as "I want to know more" and "Tell me more". The list of titles is an example of a "list of gist" related to the technology of the present disclosure, and the specific title is an example of a "predetermined gist" related to the technology of the present disclosure.

[0044] The granting unit 290D grants a reward to the posting user who created the created text associated with the title output to the smart device 14, and to the posting user who created the created text output to the smart device 14. Specifically, the granting unit 290D grants a monetary reward to the posting user according to the number of views. In addition, the timing and method of granting the reward are not particularly limited, but for example, the granting unit 290D deposits an amount according to the number of views into the bank account of the posting user at a predetermined cycle.

[0045] Fig. 4 shows an example of an operation flow of the first identification process in which the identification processing unit 290 generates a problem that can be solved by the content of the created text and a title of the created text. The operation flow shown in Fig. 4 is performed by the identification processing unit 290 reading the identification processing program 56 from the storage 32, expanding it in the RAM 30, and executing it. The operation flow shown in Fig. 4 is automatically executed repeatedly, for example, at regular intervals.

[0046] 4, the identification processing unit 290 acquires input data indicating a user input accepted by the smart device 14. Then, the identification processing unit 290 proceeds to step S11.

[0047] In step S11, the specific processing unit 290 determines whether or not the input data acquired in step S10 satisfies the first trigger condition. If the specific processing unit 290 determines that the first trigger condition is satisfied (step S11: YES), the process proceeds to step S12. On the other hand, if the specific processing unit 290 determines that the first trigger condition is not satisfied (step S11: NO), the process ends the operation flow shown in Fig. 4. As an example, if the input data acquired in step S10 is an created sentence, the specific processing unit 290 determines that the first trigger condition is satisfied.

[0048] In step S12, the identification processing unit 290 inputs the created sentence acquired in step S10 and a prompt including an instruction to generate a problem that can be solved by the content of the created sentence and a title of the created sentence as a first prompt to the data generation model 58, and acquires the result of the first identification process based on the output of the data generation model 58. For example, the identification processing unit 290 acquires text data of "I will explain how to relieve physical fatigue. First, ... (omitted)" as the created sentence. In this case, the identification processing unit 290 inputs the text "Please generate a problem that can be solved by the content of the following sentence and a title of the sentence. Sentence: I will explain how to relieve physical fatigue. First, ... (omitted)" as the first prompt to the data generation model 58. Here, the identification processing unit 290 acquires a problem and a title corresponding to the first prompt as a result of the first identification process. Then, the identification processing unit 290 proceeds to step S13.

[0049] In step S13, the specific processing unit 290 saves various information. Specifically, the specific processing unit 290 associates the assignment and title corresponding to the first prompt acquired in step S12, the created text acquired in step S10, and the posting user who created the created text, and stores them in the database 24. Then, the specific processing unit 290 proceeds to step S14.

[0050] In step S14, the identification processing unit 290 fine-tunes the data generation model 58 using the pair of the task and the title corresponding to the first prompt acquired in step S12 as learning data. Then, the identification processing unit 290 ends the operation flow shown in FIG.

[0051] Fig. 5 shows an example of an operation flow of the identification processing unit 290 performing a second identification process for generating a search intent of a browsing user and a third identification process for generating a list of titles associated with tasks corresponding to the search intent. The operation flow shown in Fig. 5 is performed by the identification processing unit 290 reading out the identification processing program 56 from the storage 32, expanding it in the RAM 30, and executing it. The operation flow shown in Fig. 5 is automatically executed repeatedly, for example, at regular intervals.

[0052] 5, the specific processing unit 290 acquires input data indicating a user input accepted by the smart device 14. Then, the specific processing unit 290 proceeds to step S21.

[0053] In step S21, the identification processing unit 290 determines whether or not the input data acquired in step S20 satisfies the second trigger condition. If the identification processing unit 290 determines that the second trigger condition is satisfied (step S21: YES), the process proceeds to step S22. On the other hand, if the identification processing unit 290 determines that the second trigger condition is not satisfied (step S21: NO), the process ends the operation flow shown in Fig. 5. As an example, if the input data acquired in step S20 is a search query, the identification processing unit 290 determines that the second trigger condition is satisfied.

[0054] In step S22, the identification processing unit 290 inputs a prompt including the search query acquired in step S20 and an instruction to inquire about the search intention of the browsing user assumed from the search query as a second prompt to the data generation model 58, and acquires a result of the second identification process based on the output of the data generation model 58. For example, it is assumed that the identification processing unit 290 acquires text data of "I've been having trouble getting rid of my fatigue lately" as a search query. In this case, the identification processing unit 290 inputs the text "Please extract the search intention of the browsing user assumed from the following search query. Search query: I've been having trouble getting rid of my fatigue lately" as a second prompt to the data generation model 58. Here, the identification processing unit 290 acquires a search intention corresponding to the second prompt as a result of the second identification process. Then, the identification processing unit 290 proceeds to step S23.

[0055] In step S23, the identification processing unit 290 inputs a prompt including an instruction to inquire about a list of titles associated with the task corresponding to the search intent corresponding to the second prompt acquired in step S22 as a third prompt to the data generation model 58, and acquires the result of the third identification process based on the output of the data generation model 58. For example, it is assumed that the identification processing unit 290 acquires text data of "I want to relieve fatigue" as the search intent corresponding to the second prompt in step S22. In this case, the identification processing unit 290 inputs the text "Please extract a list of titles associated with the task corresponding to the following search intent. Search intent: I want to relieve fatigue" as the third prompt to the data generation model 58. Here, the identification processing unit 290 acquires a list of titles corresponding to the third prompt as a result of the third identification process. Then, the identification processing unit 290 proceeds to step S24.

[0056] In step S24, the identification processing unit 290 outputs a result of the third identification processing to the viewing user's smart device 14. Specifically, the identification processing unit 290 outputs a list of titles corresponding to the third prompt acquired in step S23 to the viewing user's smart device 14. As a result, the list of titles is displayed on the display 40A of the smart device 14. Then, the identification processing unit 290 proceeds to step S25.

[0057] In step S25, the identification processing unit 290 determines whether or not interest information has been acquired. If the identification processing unit 290 determines that interest information has been acquired (step S25: YES), the process proceeds to step S26. On the other hand, if the identification processing unit 290 determines that interest information has not been acquired (step S25: NO), the process ends the operation flow shown in FIG.

[0058] In step S26, the specific processing unit 290 acquires the created text associated with the predetermined title from the database 24 and outputs it to the viewing user's smart device 14. As a result, the created text is displayed on the display 40A of the smart device 14. Then, the specific processing unit 290 ends the operation flow shown in FIG.

[0059] Next, the result of the specific process displayed on the display 40A of the viewing user's smart device 14 will be described with reference to Figs. 6 and 7. Specifically, the display examples shown in Figs. 6 and 7 show the screen of a specific app running on the smart device 14.

[0060] As shown in FIG. 6, a user input 100, an AI response 101, and a user input 102 are displayed on display 40A.

[0061] The user input 100 indicates a sentence, "Recently, I've been having trouble getting rid of fatigue," which is a text input received from a browsing user. Here, the control unit 46A of the smart device 14 transmits input data indicating the user input 100 to the data processing device 12.

[0062] The AI ​​response 101 indicates text data output from the data generation model 58. Here, the identification processing unit 290 of the data processing device 12 acquires input data indicating the user input 100 transmitted from the smart device 14. Next, the identification processing unit 290 inputs a prompt including the search query acquired as the input data and an instruction to inquire about the search intention of the browsing user assumed from the search query as a second prompt to the data generation model 58, and acquires the result of the second identification process based on the output of the data generation model 58. Next, the identification processing unit 290 inputs a prompt including an instruction to inquire about a list of titles associated with the assignment corresponding to the search intention corresponding to the second prompt acquired as a result of the second identification process as a third prompt to the data generation model 58, and acquires the result of the third identification process based on the output of the data generation model 58. Then, the identification processing unit 290 outputs a list of titles corresponding to the third prompt acquired as a result of the third identification process to the smart device 14. As a result, the list of titles is displayed as the AI ​​response 101 on the display 40A of the smart device 14. Specifically, Figure 6 displays a list of AI response 101, which reads, "Here are three recommended titles for you: 1. How to make your body less susceptible to fatigue 2. Sleeping techniques that relieve fatigue 3. Recipes that will give you plenty of stamina."

[0063] The user input 102 indicates a sentence, “2. I would like to know more about a sleep method that relieves fatigue,” which is a text input received from a browsing user. Here, the control unit 46A of the smart device 14 transmits input data indicating the user input 102 to the data processing device 12.

[0064] As shown in FIG. 7, an AI response 103 is displayed on display 40A. The AI ​​response 103 indicates text data output from the data generation model 58. Here, the specific processing unit 290 of the data processing device 12 acquires input data indicating the user input 102 transmitted from the smart device 14. Next, the specific processing unit 290 determines that interest information has been acquired based on the input data. In this case, the specific processing unit 290 acquires a created sentence associated with the predetermined title "Sleeping method that relieves fatigue" from the database 24 and outputs it to the viewing user's smart device 14. As a result, the created sentence is displayed as the AI ​​response 103 on the display 40A of the smart device 14. Specifically, in FIG. 7, the created sentence "I will explain how to relieve physical fatigue. First, ... (omitted)" is displayed as the AI ​​response 103.

[0065] As described above, in the data processing device 12, the identification processing unit 290 inputs the acquired created sentence and a prompt including an instruction to generate a problem that can be solved by the content of the created sentence and a title of the created sentence as a first prompt to the data generation model 58, and generates a problem and a title corresponding to the first prompt. In addition, the identification processing unit 290 associates the problem and title corresponding to the generated first prompt with the created sentence and the posting user who created the created sentence, and stores them in the database 24. In addition, the identification processing unit 290 inputs a prompt including the acquired search query and an instruction to inquire about the search intention of the browsing user assumed from the search query as a second prompt to the data generation model 58, and generates a search intention corresponding to the second prompt. In addition, the identification processing unit 290 inputs a prompt including an instruction to inquire about a list of titles associated with the problem corresponding to the search intention corresponding to the generated second prompt as a third prompt to the data generation model 58, and generates a list of titles corresponding to the third prompt. Then, the specific processing unit 290 outputs a list of titles corresponding to the third prompt to the smart device 14, and, if interest information is acquired, outputs the created text associated with the predetermined title to the smart device 14.

[0066] With the above configuration, the data processing device 12 can output a list of titles associated with issues corresponding to the search intent of the browsing user to the smart device 14. Furthermore, the data processing device 12 can output a created text in which the browsing user has shown interest from the list of titles to the smart device 14. As a result, the data processing device 12 can respond appropriately to user input and output a list of titles and created text suitable for the browsing user to the smart device 14 of the browsing user.

[0067] Furthermore, in the data processing device 12, the specific processing unit 290 provides a reward to the posting user who created the composition text associated with the title output to the viewing user's smart device 14, and to the posting user who created the composition text output to the smart device 14. In this way, the data processing device 12 can increase the posting user's motivation to create composition texts.

[0068] Furthermore, in the data processing device 12, the specific processing unit 290 fine-tunes the data generation model 58 using a pair of a task and a title corresponding to the generated first prompt as learning data. This allows the data processing device 12 to generate a task and a title corresponding to the first prompt with higher accuracy than when fine-tuning is not performed.

[0069] Second Embodiment Next, a second embodiment of the data processing system 10 according to the present invention will be described while omitting or simplifying parts that overlap with the above embodiment.

[0070] Fig. 8 is a second block diagram showing an example of the functional configuration of the specific processing unit 290. As shown in Fig. 8, the specific processing unit 290 includes an acquisition unit 290A, a processing unit 290B, an output unit 290C, an assignment unit 290D, and a notification unit 290E.

[0071] When the similarity between multiple created sentences stored in database 24 is equal to or greater than a predetermined value and the multiple created sentences are created by different posting users, notification unit 290E notifies the initial user, who is the posting user who created the created sentence that was first acquired by acquisition unit 290A among the multiple created sentences, of the existence of a similar created sentence.

[0072] The notification unit 290E periodically acquires the multiple created sentences stored in the database 24 and extracts the multiple created sentences whose similarity is equal to or greater than a predetermined value. As an example, the notification unit 290E uses cosine similarity as the similarity to determine how similar the multiple created sentences are. Then, when the multiple created sentences whose cosine similarity is equal to or greater than a predetermined value are created by different posting users, the notification unit 290E notifies the smart device 14 of the initial user of the existence of a similar created sentence.

[0073] The acquiring unit 290A acquires a deletion instruction from the initial user as input data. For example, the initial user transmits text data of “Please delete similar created sentences” as a deletion instruction to the data processing device 12 via the smart device 14.

[0074] When the acquisition unit 290A acquires a deletion instruction from the initial user, the processing unit 290B deletes from the database 24 sentences created by other posting users that are similar to the sentences created by the initial user.

[0075] With the above configuration, the data processing device 12 can prevent text created by other posting users that is assumed to imitate the text created by the original user from being output to the viewing user's smart device 14.

[0076] (Third embodiment) Next, a third embodiment of the data processing system 10 according to the present invention will be described while omitting or simplifying parts that overlap with the above-described embodiments.

[0077] The functional configuration of the specific processing unit 290 according to the third embodiment is, for example, the functional configuration shown in FIG. 8, similar to that of the second embodiment.

[0078] The acquisition unit 290A acquires the browsing history of the created text by the browsing user as input data. The acquisition unit 290A stores the acquired browsing history in the database 24 in association with the browsing user.

[0079] The processing unit 290B inputs a prompt including the search query acquired as input data by the acquisition unit 290A, the browsing history of the text created by the viewing user who entered the input data stored in the database 24, and an instruction to inquire about the viewing user's search intention assumed from the search query, into the data generation model 58 as a second prompt, and generates a search intention corresponding to the second prompt.

[0080] With the above configuration, the data processing device 12 can generate a search intention based on the browsing history of the text created by the browsing user. As a result, the data processing device 12 can generate the search intention of the browsing user with higher accuracy than when the browsing history of the text created by the browsing user is not input to the data generation model 58.

[0081] (Fourth embodiment) Next, a fourth embodiment of the data processing system 10 according to the present invention will be described while omitting or simplifying parts that overlap with the above-described embodiments.

[0082] The functional configuration of the specific processing unit 290 according to the fourth embodiment is, for example, the functional configuration shown in FIG. 8, similar to that of the second embodiment.

[0083] The acquiring unit 290A acquires user information indicating attributes of the viewing user as input data. The user information is information such as the viewing user's age, sex, hobbies, special skills, and occupation input in advance by the viewing user.

[0084] When the list of titles corresponding to the third prompt generated by the processing unit 290B includes an inappropriate title that is not suitable for the attributes of the viewing user indicated by the user information, the output unit 290C outputs a list of titles excluding the inappropriate titles to the viewing user's smart device 14. An inappropriate title is a title that includes a term that is assumed to be inappropriate for each attribute of the viewing user (e.g., age or gender, etc.). The terms that are inappropriate titles for each attribute of the viewing user are, for example, manually set in advance in the data processing device 12. An inappropriate title is an example of an "inappropriate gist" related to the technology of the present disclosure.

[0085] For example, if there is a list of five titles corresponding to the third prompt, and among these five titles there are two inappropriate titles that are not suitable for the attributes of the viewing user indicated by the user information, the output unit 290C outputs a list of three titles excluding the two inappropriate titles to the viewing user's smart device 14.

[0086] With the above configuration, the data processing device 12 can filter created documents that can be viewed by a viewing user according to the attributes of the viewing user.

[0087] (others) In the above embodiment, the gist of the created text is described as the "title of the created text", but as described above, the gist of the created text may include at least one of the title and summary of the created text. Therefore, in the above embodiment, the gist of the created text may be the "summary of the created text", or the gist of the created text may be the "title and summary of the created text".

[0088] If the gist of the created text is the "title and summary of the created text", the identification processing unit 290 performs the identification processing as follows. In this case, the identification processing unit 290 inputs the acquired created text and a prompt including an instruction to generate a problem that can be solved by the content of the created text and a title and summary of the created text as a first prompt to the data generation model 58, and generates a problem corresponding to the first prompt, as well as the title and summary. The identification processing unit 290 also associates the problem corresponding to the generated first prompt, the title and summary, the created text on which the problem, the title and summary are based, and the posting user who created the created text, and stores them in the database 24. The identification processing unit 290 also fine-tunes the data generation model 58 using the pair of the problem and title corresponding to the generated first prompt and the pair of the problem and summary corresponding to the generated first prompt as learning data. The identification processing unit 290 also inputs a prompt including an instruction to inquire about a list of titles or abstracts associated with the task corresponding to the search intent corresponding to the generated second prompt as a third prompt to the data generation model 58, and generates a list of titles or abstracts corresponding to the third prompt. Then, the identification processing unit 290 outputs the list of titles or abstracts corresponding to the generated third prompt to the smart device 14.

[0089] The emotion identification model 60 may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 60 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping.

[0090] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0091] These emotions are distributed in the three o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0092] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0093] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0094] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0095] The emotion identification model 60 inputs user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0096] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0097] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0098] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0099] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0100] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing the specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0101] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0102] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0103] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0104] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above description and illustrations, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above description and illustrations omit explanations of technical common sense that do not require explanation in order to enable the implementation of the technology of the present disclosure.

[0105] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0106] 10 Data Processing System 12 Data Processing Device 14 Smart Devices

Claims

1. an acquisition unit for acquiring input data indicative of a user input; A processing unit that performs a specific process using a generative model that generates information according to the input data; an output unit that outputs a result of the specific processing to an electronic device; The acquisition unit is A created sentence which is a sentence created by a first user is obtained as the input data; The processing unit includes: inputting the created sentence acquired by the acquisition unit and a prompt including an instruction to generate a problem that can be solved by the content of the created sentence and a summary of the created sentence into the generation model as a first prompt, thereby generating a problem and a summary corresponding to the first prompt; storing the generated task and summary corresponding to the first prompt in a storage unit in association with the created text; inputting a prompt including the search query acquired by the acquisition unit as the input data and an instruction to inquire about a search intention of a second user assumed from the search query into the generative model as a second prompt, thereby generating a search intention corresponding to the second prompt; inputting a prompt including an instruction to inquire about a list of abstracts related to a problem corresponding to the search intent corresponding to the generated second prompt into the generation model as a third prompt, thereby generating a list of abstracts corresponding to the third prompt; The output unit is outputting, to the electronic device, a list of gist corresponding to the third prompt generated by the processing unit, and when the acquisition unit acquires the input data indicating an interest of the second user in a specific gist in the list of gist, outputting the created text associated with the specific gist to the electronic device. Data processing device.

2. The processing unit includes: storing in the storage unit a task and an outline corresponding to the generated first prompt, the created text, and the first user in association with each other; a rewarding unit that rewards the first user who created the created text associated with the gist output to the electronic device and the first user who created the created text output to the electronic device; 2. A data processing apparatus according to claim 1.

3. The processing unit includes: fine-tuning the generative model using a pair of a problem and a gist corresponding to the first prompt as training data; 2. A data processing apparatus according to claim 1.

4. a notification unit that notifies an initial user, who is the first user who created the created sentence first acquired by the acquisition unit among the multiple created sentences, of the existence of a similar created sentence when the similarity between the multiple created sentences stored in the storage unit is equal to or greater than a predetermined value and the multiple created sentences are created by different first users; When the acquisition unit acquires a deletion instruction from the initial user as the input data, the processing unit deletes the created sentence created by the other first user that is similar to the created sentence created by the initial user from the storage unit.

3. A data processing apparatus according to claim 2.

5. The processing unit inputs a prompt including the search query, a browsing history of the created text by the second user, and an instruction to inquire about the search intention into the generative model as the second prompt, and generates a search intention corresponding to the second prompt.

2. A data processing apparatus according to claim 1.

6. The acquisition unit acquires user information indicating an attribute of the second user as the input data, When an inappropriate summary that is not suitable for the attribute of the second user indicated by the user information is included in the list of summaries corresponding to the third prompt generated by the processing unit, the output unit outputs a list of summaries excluding the inappropriate summary to the electronic device.

2. A data processing apparatus according to claim 1.

7. Obtaining input data indicative of user input; performing a determination process using a generative model that generates information according to the input data; outputting a result of the specific processing to an electronic device; A created sentence which is a sentence created by a first user is obtained as the input data; inputting the acquired created sentence and a prompt including an instruction to generate a problem that can be solved by the content of the created sentence and a summary of the created sentence into the generation model as a first prompt, thereby generating a problem and a summary corresponding to the first prompt; storing the generated task and summary corresponding to the first prompt in a storage unit in association with the created text; inputting a search query acquired as the input data and a prompt including an instruction to inquire about a search intention of a second user assumed from the search query into the generative model as a second prompt, thereby generating a search intention corresponding to the second prompt; inputting a prompt including an instruction to inquire about a list of abstracts related to a problem corresponding to the search intent corresponding to the generated second prompt into the generation model as a third prompt, thereby generating a list of abstracts corresponding to the third prompt; outputting to the electronic device a list of summaries corresponding to the generated third prompt, and when the input data indicating an interest of the second user in a specific summary in the list of summaries is acquired, outputting to the electronic device the created text associated with the specific summary. A data processing method in which processing is performed by a computer.

8. Obtaining input data indicative of user input; performing a determination process using a generative model that generates information according to the input data; outputting a result of the specific processing to an electronic device; A created sentence which is a sentence created by a first user is obtained as the input data; inputting the acquired created sentence and a prompt including an instruction to generate a problem that can be solved by the content of the created sentence and a summary of the created sentence into the generation model as a first prompt, thereby generating a problem and a summary corresponding to the first prompt; storing the generated task and summary corresponding to the first prompt in a storage unit in association with the created text; inputting a search query acquired as the input data and a prompt including an instruction to inquire about a search intention of a second user assumed from the search query into the generative model as a second prompt, thereby generating a search intention corresponding to the second prompt; inputting a prompt including an instruction to inquire about a list of abstracts related to a problem corresponding to the search intent corresponding to the generated second prompt into the generation model as a third prompt, thereby generating a list of abstracts corresponding to the third prompt; outputting to the electronic device a list of summaries corresponding to the generated third prompt, and when the input data indicating an interest of the second user in a specific summary in the list of summaries is acquired, outputting to the electronic device the created text associated with the specific summary. A data processing program for causing a computer to execute processing.

Images